{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:05:24Z","timestamp":1770314724838,"version":"3.49.0"},"reference-count":23,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["22BJY022"],"award-info":[{"award-number":["22BJY022"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012174","name":"Hunan Office of Philosophy and Social Science","doi-asserted-by":"publisher","award":["21YBA117"],"award-info":[{"award-number":["21YBA117"]}],"id":[{"id":"10.13039\/501100012174","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>For cross\u2010city traffic prediction, the significant heterogeneity of traffic data across cities and the requirement for privacy protection make it challenging for conventional centralized spatiotemporal graph modeling techniques to balance predictive performance and data security. Therefore, this paper proposes AT\u2010SPNet, a personalized federated spatiotemporal modeling approach specifically designed for cross\u2010city traffic prediction. This method decouples the spatiotemporal modeling paths through the construction of a shared temporal branch and a hidden local spatial branch, thereby mitigating the heterogeneity of cross\u2010city traffic data while preserving privacy. In the temporal branch, Gated Recurrent Units and a multi\u2010head attention mechanism are incorporated to capture temporal dependencies, and a Squeeze\u2010and\u2010Excitation module is employed to enhance the extraction of informative features. In the spatial branch, a Spatial Attention Fusion module based on a triple\u2010attention mechanism is designed to capture spatial features from multiple spatial perspectives, combined with static graph convolution and dynamic graph attention to construct a dual\u2010modal information fusion path. Furthermore, to alleviate the adverse effects of cross\u2010city data heterogeneity in federated training, a personalized federated learning strategy is introduced, which enables differentiated fusion of client spatial features without sharing raw data. Experiments on four real\u2010world traffic datasets demonstrate that AT\u2010SPNet outperforms existing methods in both prediction accuracy and cross\u2010city generalization, validating the effectiveness and practical applicability of the proposed approach for cross\u2010city traffic prediction.<\/jats:p>","DOI":"10.1002\/cpe.70577","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:57:38Z","timestamp":1769165858000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AT\u2010SPNet: A Personalized Federated Spatio\u2010Temporal Modeling Method for Cross\u2010City Traffic Prediction"],"prefix":"10.1002","volume":"38","author":[{"given":"Ying","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering Hunan University of Science and Technology  Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9558-6832","authenticated-orcid":false,"given":"Renjie","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Hunan University of Science and Technology  Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Hunan University of Science and Technology  Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Hunan University of Science and Technology  Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanxi","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Hunan University of Science and Technology  Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-020-00151-z"},{"key":"e_1_2_12_3_1","doi-asserted-by":"crossref","unstructured":"L.Wang \u201cCross\u2010City Transfer Learning for Deep Spatio\u2010Temporal Prediction \u201d(2018). arXiv preprint arXiv:1802.00386.","DOI":"10.24963\/ijcai.2019\/262"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3157056"},{"key":"e_1_2_12_5_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Yao H.","year":"2019"},{"key":"e_1_2_12_6_1","unstructured":"L.Wang \u201cCrowd Flow Prediction by Deep Spatio\u2010Temporal Transfer Learning \u201d(2018). arXiv preprint arXiv:1802.00386."},{"key":"e_1_2_12_7_1","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Pan Z.","year":"2019"},{"key":"e_1_2_12_8_1","volume-title":"Proceedings of the 31st ACM International Conference on Information and Knowledge Management","author":"Tang Y.","year":"2022"},{"key":"e_1_2_12_9_1","volume-title":"Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI)","author":"Zhang Y.","year":"2024"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120482"},{"key":"e_1_2_12_11_1","volume-title":"Proceedings of the Artificial Intelligence and Statistics (AISTATS)","author":"McMahan B.","year":"2017"},{"key":"e_1_2_12_12_1","first-page":"21394","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Dinh C. T.","year":"2020"},{"key":"e_1_2_12_13_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li T.","year":"2021"},{"key":"e_1_2_12_14_1","unstructured":"J.Li \u201cPersonalized Federated Learning With Similarity Information Supervisor\u201dUnpublished manuscript."},{"key":"e_1_2_12_15_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Collins L.","year":"2021"},{"key":"e_1_2_12_16_1","unstructured":"Z.Zeng Effective and Efficient Cross\u2010City Traffic Knowledge Transfer: A Privacy\u2010Preserving Perspective(2025). arXiv preprint arXiv:2503.11963."},{"key":"e_1_2_12_17_1","unstructured":"A.Banik D. G. H. S.Carvalho andR.Dividino Federated Learning With Graph\u2010Based Aggregation for Traffic Forecasting(2025). arXiv preprint arXiv:2507.09805."},{"key":"e_1_2_12_18_1","unstructured":"A.Fallah A.Mokhtari andA.Ozdaglar Personalized Federated Learning: A Meta\u2010Learning Approach(2020). arXiv Preprint arXiv:2002.07948."},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103772"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.129001"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/smartcities8040126"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111637"},{"key":"e_1_2_12_23_1","doi-asserted-by":"crossref","unstructured":"B.Yu H.Yin andZ.Zhu \u201cSpatio\u2010Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting \u201d(2017). arXiv preprint arXiv:1709.04875.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70577","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70577","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T03:07:50Z","timestamp":1770260870000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/cpe.70577"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70577","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]},"assertion":[{"value":"2025-10-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70577"}}